Entertainment Discovery Rebellion - Project Context
You are working on Entertainment Discovery Rebellion, an MCP (Model Context Protocol) server that solves entertainment choice paralysis through conversational AI media recommendations.
Critical Project Context
**The 5 most important things to know:**
1. **Project**: Entertainment Discovery Rebellion - MCP server providing conversational AI media recommendations
2. **Hackathon**: TasteRay AI Creative Hackathon (June 16-29, 2025) - competing against 833 participants
3. **Technical Approach**: MCP server with memory nodes for subscription-aware recommendations (NOT a web app)
4. **Problem**: Users face 40,000+ daily content choices with complex subscription contexts (shared Netflix, family HBO Max, etc.)
5. **Status**: Planning complete, ready for implementation - Week 1 focuses on API integration and basic content discovery
Technical Architecture
Core Stack
**Foundation**: Open-source memory MCP server**APIs**: Watchmode (streaming availability) + TMDB (metadata)**Intelligence**: AI context analysis for mood, time, companions, platform access**Interface**: Conversational through Claude (not traditional UI)MCP Tools Structure
```
discover_content_with_context() - Main recommendation engine
get_platform_availability() - Real-time streaming availability
update_subscription_context() - Memory node management
learn_from_feedback() - Adaptive preference evolution
```
Memory Node Patterns
Personal subscriptions (individual Netflix, Prime)Shared access (partner's Disney+)Contextual availability (family HBO Max on weekends)Geographic restrictionsTemporal usage patternsImplementation Approach
Week 1 Priorities (June 19-21)
1. API Integration: Connect and test Watchmode + TMDB
2. Basic Content Discovery: Core recommendation tool functional
3. Memory Integration: Subscription context storage/retrieval
4. Milestone: Basic system working
Week 2 Priorities (June 22-29)
1. Context Intelligence: Sophisticated situation analysis
2. Conversation Flow: Natural language interaction refinement
3. Demo Preparation: 10-minute showcase scenarios
4. Competition Submission: Final polish and documentation
API Strategy
**Primary**: Watchmode (1,000 req/day) + TMDB (1,000 req/day)**Backup**: Streaming Availability API, uNoGS, OMDb**Fallback**: Curated dataset of ~1,000 popular titles for demo reliability**Scope**: US market focus for MVPCompetitive Advantages
What Competitors Will Build
Standard web apps with forms/filtersStatic recommendation algorithmsMock data or limited API integrationTraditional UI patterns (grids, lists, search)What You're Building
**Conversational AI Interface**: Natural language vs forms**Live Streaming Data**: Real-time availability vs static datasets**Context Intelligence**: Understanding viewing situations vs simple preferences**Memory-Powered Learning**: Persistent subscription contexts**MCP Architecture**: Cutting-edge AI protocol vs standard web techDevelopment Guidelines
Code Quality
Follow existing codebase patterns and conventionsPrioritize working functionality over perfect architectureFocus on demo-ready features vs comprehensive coverageImplement error handling for API rate limits and failuresMemory Management
Use memory nodes for persistent subscription contextsStore conversation history for learning patternsCache popular content for demo performanceBalance memory usage with context richnessAPI Integration
Implement multi-API fallback strategy for reliabilityCache responses to manage rate limits effectivelyUse async requests for performance optimizationProvide graceful degradation on errorsProject Documentation
`/docs/Project-Scope-Plan.md` - Overall objectives and timeline`/docs/Task-Tracking-Log.md` - Current progress and next steps`/docs/Module-Spec-Content-Discovery.md` - Technical implementation details`/docs/Decision-Registry.md` - Key architectural choices and rationale`/docs/Project-Constitution.md` - Collaboration principles and communication guidelinesCurrent Task Priorities
Immediate Next Steps (from Task-Tracking-Log.md)
1. **TSK-011**: Acquire and test API keys (Watchmode, TMDB)
2. **TSK-006**: Define memory integration strategy
3. **TSK-007**: Implement basic content discovery tool
4. **TSK-008**: Set up subscription context memory nodes
Weekly Milestones
**June 21**: Foundation Complete (memory + basic discovery working)**June 24**: Subscription Intelligence (complex context handling)**June 27**: Demo Ready (compelling 10-minute showcase)**June 29**: Submission Polish (final documentation)Demo Requirements (10-minute showcase)
1. **Context Setup**: User describes complex viewing situation
2. **Subscription Intelligence**: System recognizes available platforms in context
3. **Recommendation Generation**: 3 perfect suggestions with explanations
4. **Learning Demonstration**: Show adaptation based on feedback
5. **Competitive Differentiation**: Highlight conversational AI vs typical systems
Success Metrics
**Functional**: 3 relevant recommendations in <10 seconds**Accuracy**: Matches user context and actual platform availability**Intelligence**: Clear AI understanding vs algorithmic filtering**Impact**: Judges appreciate technical sophistication + practical valueCollaboration Framework
When working on this project:
**Focus on needs vs wants**: Solve real entertainment choice paralysis vs perfect algorithms**Leverage technical expertise**: Use MCP architecture for competitive advantage**Challenge conventions**: Suggest sophisticated alternatives to standard patterns**Prioritize hackathon victory**: Balance innovation with timeline constraints**Evaluate progress regularly**: Assess against competition objectivesCommunication Style
Direct, honest assessment of technical challenges and progressFocus on practical implementation over theoretical perfectionBalance sophisticated demonstration with timeline constraintsRegular progress evaluation against competition objectives---
**Project Essence**: AI-powered conversational media advisor that understands your entertainment life, built with cutting-edge MCP architecture to win the TasteRay hackathon through technical sophistication and practical problem solving.